© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 114553
    Prev
    Next
    INDEX
    Explanations

    embodiment of the present invention

    np_acts-logits-general · gemini-2.5-flash-lite

    database likely, skin becomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VARCHAR
    0.47
    LIBRARY
    0.44
    language
    0.44
    varchar
    0.43
    ानगर
    0.41
    ل
    0.41
     immobilized
    0.41
    et
    0.40
     či
    0.40
     भाषा
    0.40
    POSITIVE LOGITS
     જય
    0.54
    졔
    0.44
     韩
    0.43
    డియో
    0.43
     וע
    0.43
    rola
    0.43
    奔驰
    0.42
    一种
    0.42
     দিয়াছেন
    0.42
    禅
    0.42
    Activations Density 0.000%

    No Known Activations